Yanjun Feng

Papers

Total Citations

H-Index

About

Yanjun Feng is a leading researcher in computer vision and affective computing, with a primary focus on advancing facial expression recognition (FER) technologies for human-robot interaction. His most cited work, "Facial Expression Recognition Using Pose-Guided Face Alignment and Discriminative Features Based on Deep Learning" (2021, 51 citations), addresses critical real-world challenges in FER, including lighting variations, occlusion, and pose variations. Feng's key contribution lies in developing a pose-guided face alignment framework that enhances model robustness by integrating discriminative deep learning features, significantly improving recognition accuracy under non-ideal conditions. This work is foundational for enabling robots to better interpret human emotions in dynamic environments. Beyond this paper, Feng's research portfolio spans deep learning architectures and multimodal emotion recognition, with his citation impact reflecting growing interest in deploying FER systems in autonomous systems and assistive robotics. His achievements include advancing practical solutions for occlusion-robust recognition, a persistent bottleneck in the field. For students and researchers, Feng's work exemplifies how combining geometric alignment with deep feature learning can bridge the gap between laboratory benchmarks and real-world deployment in human-aware AI systems.